What an AI can and cannot see
Three blind spots. Each of them is the kind of thing you discover after twenty minutes of wondering why the assistant is being obtuse, so they are worth knowing first.
1. It cannot see images
This is the one that catches everybody.
An assistant reading an issue gets the text: the title, the description, the fields, the comments. It does not get the pictures. A screenshot attached to an issue or a comment is invisible to it - it can see that an attachment exists, but not what is in it.
So an issue whose entire content is "see attached image" is, to an assistant, an issue with no content.
What to do: paste the screenshot into the chat as well. The assistant can see images you give it directly; it just cannot fetch the ones in the tracker.
What to avoid: putting the actual information only in a picture. A one-line written description alongside the image costs nothing and makes the issue readable by everything - the assistant, the API, a search, and a colleague on a phone.
2. It cannot see the order of cards on the board
If you drag cards up and down inside a column to show what matters most, that ordering lives in your browser. It is not stored on the issue.
An assistant asked "what should I do first?" sees only the Priority field. It has no idea about the order you so carefully arranged.
What to do: if the ordering is a message to other people or to an assistant, put it in Priority. If it is a note to yourself, carry on - just do not expect anything else to read it. See Board view and grouping.
3. It only accepts the values your project allows
Ask for a status your project does not have and the assistant will be refused, told the real list, and told to ask you rather than substitute something.
That is working as intended, not a failure. An assistant that quietly picked the nearest-looking value would fill the tracker with vocabulary nobody chose.
What to do: either use one of the listed values, or add the one you want under Project options. The fix is in the project settings, not in the assistant.
Also worth knowing
It cannot delete anything - see Connecting an AI assistant.
It cannot add people to a project. Adding somebody is a decision a person makes in the app. An assistant can assign an issue to anybody already on the project - including placeholder people - but if the person you name is not there, it will say so and leave the issue unassigned rather than guessing.
It may be signed in as a different account than you expect, if you set the connector up with another login. When in doubt, ask it who it is signed in as.
It sees the standard's words, not the app's. It will talk about topics and stages where you say issues and milestones. See Issue, task or topic?, or just ask it to use your words.
What it is genuinely good at
Reading across many issues and telling you what is there: what is assigned to you and overdue, which issues have gone quiet, what changed on something this week, summarising a long comment thread.
Those are all text, and text is the part it can see.